INDEX

Explanations

terminology related to obstacles or hindrances

oai_token-act-pair · gpt-3.5-turbo

terms related to restrictions and obstacles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Stars

-0.73

Values

-0.72

Truth

-0.70

Score

-0.67

 Profession

-0.66

 Stories

-0.65

 headlined

-0.65

 Images

-0.63

 Featured

-0.62

LV

-0.60

POSITIVE LOGITS

 inhib

0.84

 restricting

0.83

 preventing

0.80

downs

0.79

 inhibition

0.78

 imposed

0.76

ption

0.76

DOWN

0.75

gap

0.74

 halting

0.71

Activations Density 0.175%

terminology related to obstacles or hindrances

terms related to restrictions and obstacles

No Comments

No Known Activations